Predicting Online Fraudulent Transaction Using Machine Learning

Fraudulent online transactions have caused significant damage and loss to individuals and companies over a period of time. There has been an increase in online frauds with the progression of state-of-the-art technologies and worldwide communication. The design of efficient fraud detection algorithms is critical for reducing these losses. Machine learning and statistical techniques play a vital role in the detection of fraudulent transactions. Fraud detection model implementation is particularly challenging due to the lack of data, sensitive nature of data and the unbalanced class distributions. It is tough to draw inference and build better models due to the confidentiality of the records. In this paper we aim to focus on the particular problems: i) role of sampling in the presence of class imbalance (i.e. non fraudulent transactions are more in percentage of the total transactions), ii) to build and analyze various machine learning models, iii) to assess and validate the performances of different fraud detection techniques. This paper has research directions towards applying machine learning for data analysis. We have designed and assessed a prototype of a fraudulent transactions detection system which will be able to meet real-world demands and increase the security of transactions for the customers.